Authors: Klinkenberg, Ralf
Scholz, Martin
Title: Boosting classifiers for drifting concepts
Language (ISO): en
Abstract: This paper proposes a boosting-like method to train a classifier ensemble from data streams. It naturally adapts to concept drift and allows to quantify the drift in terms of its base learners. The algorithm is empirically shown to outperform learning algorithms that ignore concept drift. It performs no worse than advanced adaptive time window and example selection strategies that store all the data and are thus not suited for mining massive streams.
Subject Headings: Base learners
Boosting-like method
Classifier ensemble
Data stream
Drift
Mining massive streams
URI: http://hdl.handle.net/2003/22236
http://dx.doi.org/10.17877/DE290R-14320
Issue Date: 2006-03-16T13:29:57Z
Appears in Collections:Sonderforschungsbereich (SFB) 475

Files in This Item:
File Description SizeFormat 
tr06-06.pdfDNB327.53 kBAdobe PDFView/Open


This item is protected by original copyright



This item is protected by original copyright rightsstatements.org